Zark / README.md
Mfonkown's picture
No (#1)
5e97efa verified
metadata
license: unknown
datasets:
  - fka/awesome-chatgpt-prompts
  - EssentialAI/essential-web-v1.0
  - microsoft/rStar-Coder
  - FreedomIntelligence/ShareGPT-4o-Image
  - NousResearch/Hermes-3-Dataset
  - HuggingFaceFW/fineweb-2
  - google-research-datasets/go_emotions
  - ccdv/govreport-summarization
  - Bingsu/KSS_Dataset
  - bigcode/the-stack-v2
  - TIGER-Lab/WebInstruct-verified
  - OctoThinker/MegaMath-Web-Pro-Max
  - Research-EAI/essential-web-1t-sample-fdc-partitioned
  - drt/complex_web_questions
  - databricks/databricks-dolly-15k
  - open-r1/Mixture-of-Thoughts
  - OpenCoder-LLM/opc-sft-stage2
  - openbmb/Ultra-FineWeb
  - Intelligent-Internet/ChatDoctor-RL
  - CyberNative/Code_Vulnerability_Security_DPO
  - PosterCraft/Text-Render-2M
  - institutional/institutional-books-1.0
  - common-pile/caselaw_access_project
language:
  - av
  - aa
  - ae
  - ak
  - am
  - ar
  - ay
  - ba
  - be
  - bh
  - bm
  - bo
metrics:
  - accuracy
  - bertscore
  - bleu
  - bleurt
  - brier_score
  - cer
  - character
  - charcut_mt
  - chrf
  - code_eval
base_model:
  - Zarkit/Gpt2ESP-finetuned-p
  - nanonets/Nanonets-OCR-s
  - moonshotai/Kimi-K2-Instruct
  - Menlo/Jan-nano
  - google/gemma-3n-E4B-it
  - oongaboongahacker/Gemini-Nano
  - THUDM/GLM-4.1V-9B-Thinking
new_version: google/gemma-3n-E4B-it
pipeline_tag: reinforcement-learning
library_name: adapter-transformers
tags:
  - code
  - English